Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only give readOnlyHint/openWorldHint; the description adds real behavior: it returns unsigned steps, the `from` wallet is used for a dry-run, the wallet signs and sends itself, OwlGate never holds funds, and the seller pays a 0.75% fee out of the price. Gaps remain on token approval/allowance requirements and whether partial fills are possible, which matter for a Seaport fill.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Roughly four dense sentences, front-loaded with the core action and chain, then side-specific branches, then the fee and signing model. The "side buy:"/"side sell:" fragments are terse but readable; nothing is redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description only says "unsigned steps" without describing the payload shape (transaction list vs typed data) that an agent would need to hand to a wallet, and it omits approval prerequisites. For a 4-parameter multi-branch transaction-builder this is adequate but leaves real operational gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 75%, and the description compensates well: `hash` is defined per side (ask.hash for buy, offer or collection-offer hash for sell, optional with a default), `v` is scoped to sell only, and `from` is tied to the dry-run. Only `side`'s enum values are already self-documenting, so the added meaning is above baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

"Unsigned steps to take an open order on the X Layer voucher market (Seaport, chain 196)" gives a specific verb, resource and protocol context, then splits the two modes: buy pays a listing in OKB, sell accepts an offer on a voucher you hold. An agent can distinguish this from xl_market (read listings) or xl_build_order (create an order) without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description routes the agent clearly across use cases: buy requires ask.hash from xl_market; sell takes v = voucher id and an optional hash defaulting to the best open offer or collection offer. It does not mention when to prefer xl_build_order, xl_post_order or xl_cancel, but the fill-vs-create-vs-cancel split is implicit enough to act on.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.